INDEX

Explanations

names of individuals, particularly in the context of roles or accomplishments

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vent

-0.14

OfSize

-0.14

vention

-0.14

amarin

-0.14

 recep

-0.14

Ign

-0.13

 indu

-0.13

Å¯j

-0.13

.ht

-0.13

amura

-0.13

POSITIVE LOGITS

ael

0.16

mgr

0.15

è¾Ľ

0.15

RIES

0.14

ries

0.14

.presentation

0.13

.dict

0.13

ÐµÐ»Ð¾Ð²

0.13

.Requires

0.13

Activations Density 0.109%

names of individuals, particularly in the context of roles or accomplishments

No Comments

No Known Activations